YouTube Transcribe

Exposes a single tool to fetch or generate YouTube video transcripts through MCP

python

5

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "jackhp-mcp-youtube-transcribe": {
      "command": "python",
      "args": [
        "mcp_server.py"
      ]
    }
  }
}

You have an MCP server that exposes a single tool to fetch transcripts for YouTube videos. It first tries to obtain an official transcript to save time and improve accuracy, and if none is available it downloads the video audio and transcribes it locally with Whisper. This makes it easy to integrate YouTube transcription into your systems through the MCP protocol.

How to use

You connect to the MCP server using any client that supports the MCP protocol over stdio. The server exposes one primary tool called get_youtube_transcript. To use it, provide a natural language query describing the video you want to transcribe and, optionally, request Whisper transcription to skip the official transcript check.

How to install

Prerequisites you need before installing this MCP server:

• Python 3.12 or newer

• uv for fast environment creation and dependency installation

• FFmpeg must be installed and available in your system PATH

• whisper.cpp is highly recommended and will be used first if available; Python Whisper is used as a fallback when whisper.cpp isn’t present

Install and run steps in order

Available tools

get_youtube_transcript

Fetches a transcript for a YouTube query by first attempting to retrieve an official transcript, then falls back to AI-powered local transcription using Whisper if needed.